{"id":"W4412902841","doi":"10.1037/dev0002050","title":"Investigating the validity of picture-based assessments across cultures and contexts: Evidence from young children in Kenya and the United States.","year":2025,"lang":"en","type":"article","venue":"Developmental Psychology","topic":"Early Childhood Education and Development","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Jacobs Foundation; Aga Khan Foundation","keywords":"Psychology; Developmental psychology; Test validity; Adolescent development; Psychometrics; Child development","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001368655,0.0001167978,0.0001755647,0.00006438291,0.0004877277,0.00009157968,0.0002763922,0.00008909251,0.00002594534],"category_scores_gemma":[0.0004317536,0.00007356767,0.00001878542,0.0004367064,0.001159721,0.00009420889,0.00009073254,0.0002096584,0.000001591329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007015585,"about_ca_system_score_gemma":0.0003229427,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007549286,"about_ca_topic_score_gemma":0.005419208,"domain_scores_codex":[0.9984218,0.0005836692,0.0003188711,0.0002621218,0.0001941194,0.0002193651],"domain_scores_gemma":[0.9989538,0.0006891132,0.0001304749,0.0001151669,0.00005901168,0.00005246995],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002200767,0.00002629569,0.930783,0.000003391121,0.0000332459,2.683977e-7,0.06522168,0.000003729246,0.00002995362,0.0006082378,0.001226266,0.002041887],"study_design_scores_gemma":[0.0011318,0.000008492557,0.98141,0.0001063689,0.000006910163,8.842141e-7,0.01280702,0.00001073989,0.00009124346,0.003404301,0.0009380766,0.00008421033],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9873376,0.0003966633,0.0001263471,0.01062247,0.0002785056,0.0004279117,0.0000121628,0.00001629329,0.0007820365],"genre_scores_gemma":[0.9902305,0.0003797118,0.001331008,0.007861529,0.00002051222,0.00002995987,0.00004314355,0.00000405799,0.00009958414],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05241466,"threshold_uncertainty_score":0.9990596,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0450071139547364,"score_gpt":0.4149150188432443,"score_spread":0.3699079048885079,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}